© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 15866
    Prev
    Next
    INDEX
    Explanations

    medical terms and health-related information

    oai_token-act-pair · gpt-3.5-turbo

    words associated with prescriptive and assertive tones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obyl
    -0.82
    owship
    -0.77
    olicited
    -0.76
    ufact
    -0.73
    afety
    -0.71
    odder
    -0.70
    pins
    -0.70
    atson
    -0.69
    é¾įå
    -0.69
    ournal
    -0.69
    POSITIVE LOGITS
    ive
    0.83
     pronoun
    0.80
    ãĥ£
    0.74
    ptic
    0.73
    ctive
    0.70
    rics
    0.69
     tendencies
    0.69
    tymology
    0.66
     sty
    0.66
     minded
    0.65
    Activations Density 0.018%

    No Known Activations